544 tokens per sec - the new SPEED RECORD on GPUs with Clarifai Reasoning Engine! #gptoss #ai

Clarifai
659,950 views September 25, 2025

We just launched our new Reasoning Engine cranking gpt-oss 120b to 544 tokens per second, a new throughput record for model performance on GPUs. World class speed at only $0.16 per 1M tokens - learn more here: https://www.clarifai.com/products/model-inference

Keyboard shortcuts

On. Switch them off if they collide with your assistive tools; ? still opens this sheet.

Go to

Press g then the letter.

  • gh Latest
  • gs Sources
  • gm Media
  • gv Videos
  • gp Podcasts
  • gc Calendar
  • gd Decoder
  • gz Dataviz
  • ga Datasets
  • gb Blog
  • gk Markets
  • gj Careers
  • gn Prompt Notebook

On this page

  • / Focus search, where there is one
  • t Back to top
  • ? This list
  • Esc Close